Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0039

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0039
File size: 4,466 Bytes 
4dbe1d7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
 
{
  "best_metric": 0.92,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0039/checkpoints/checkpoint-2997",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 2997,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 42.03664016723633,
      "learning_rate": 4.850126564054637e-05,
      "loss": 0.8118,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.872,
      "eval_loss": 0.40084072947502136,
      "eval_runtime": 10.9454,
      "eval_samples_per_second": 342.61,
      "eval_steps_per_second": 5.39,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.854125738143921,
      "learning_rate": 4.416794553834106e-05,
      "loss": 0.2107,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.888,
      "eval_loss": 0.36281752586364746,
      "eval_runtime": 11.0549,
      "eval_samples_per_second": 339.216,
      "eval_steps_per_second": 5.337,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 13.841835975646973,
      "learning_rate": 3.7522688315464166e-05,
      "loss": 0.0905,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8781333333333333,
      "eval_loss": 0.4262290894985199,
      "eval_runtime": 11.3781,
      "eval_samples_per_second": 329.582,
      "eval_steps_per_second": 5.185,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.25060978531837463,
      "learning_rate": 2.936701006654613e-05,
      "loss": 0.0425,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9021333333333333,
      "eval_loss": 0.39219239354133606,
      "eval_runtime": 10.5105,
      "eval_samples_per_second": 356.785,
      "eval_steps_per_second": 5.613,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.6972490549087524,
      "learning_rate": 2.0684605953398183e-05,
      "loss": 0.0174,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9077333333333333,
      "eval_loss": 0.37019091844558716,
      "eval_runtime": 10.3989,
      "eval_samples_per_second": 360.615,
      "eval_steps_per_second": 5.674,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.0008706290391273797,
      "learning_rate": 1.2522702050703538e-05,
      "loss": 0.005,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9189333333333334,
      "eval_loss": 0.3712726831436157,
      "eval_runtime": 11.1829,
      "eval_samples_per_second": 335.335,
      "eval_steps_per_second": 5.276,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.20007655024528503,
      "learning_rate": 5.865744425999756e-06,
      "loss": 0.0026,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9170666666666667,
      "eval_loss": 0.36695489287376404,
      "eval_runtime": 11.7299,
      "eval_samples_per_second": 319.697,
      "eval_steps_per_second": 5.03,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.01450725644826889,
      "learning_rate": 1.5166604150571306e-06,
      "loss": 0.0011,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9197333333333333,
      "eval_loss": 0.36201608180999756,
      "eval_runtime": 10.7995,
      "eval_samples_per_second": 347.238,
      "eval_steps_per_second": 5.463,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.0005844442639499903,
      "learning_rate": 1.3735239379197851e-11,
      "loss": 0.0006,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.92,
      "eval_loss": 0.36189159750938416,
      "eval_runtime": 11.0635,
      "eval_samples_per_second": 338.952,
      "eval_steps_per_second": 5.333,
      "step": 2997
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.482671885603328e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}